Speech-recognition plus LLM hybrid model that transcribes and can summarize or answer questions about audio
NVIDIA Canary-Qwen 2.5B is listed under Speech & Transcription Engines, in the AI Models & Local Execution category on Flocci AI Tools. Speech-recognition plus LLM hybrid model that transcribes and can summarize or answer questions about audio. It is free, with no paid plan attached, and it lives at huggingface.co.
NVIDIA Canary-Qwen 2.5B is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 399 entries on Flocci AI Tools with no upgrade path built in.
NVIDIA Canary-Qwen 2.5B does 3 things the catalog singles out: Speech-recognition plus llm hybrid model that transcribes and can summarize or answer questions about audio; topped the hugging face open asr leaderboard at release (english); cc-by-4.0 weights.
faster-whisper is the closest free alternative: it sits in the same Speech & Transcription Engines sub-category and is free. FunASR, Moonshine and NVIDIA Parakeet also start free. The full list is on the alternatives page.
See the full list →